Scenario A: designing and deconstructing AI prompts as an epistemic practice¶

Strategy · All strategies
Evidence · no claims cited

Description¶

A two-part activity treating prompt design 'not as a technical skill to be optimised, but as an epistemic practice'. In Part I students individually design 2-3 prompts to elicit depth or multiple perspectives without AI access; in Part II they analyse AI responses for epistemic breadth, assumptions and omissions, then revise at least one prompt and reflect on how question framing shapes knowledge construction. The LLM becomes 'an object of inquiry rather than a resource of authority'.

Design Implications¶

Context¶

Requirements¶

• Requires an AI-free design phase, an AI-mediated exploration phase, and an AI-free synthesis phase

Constraints¶

• Offered as a situated example for adaptation, not a fixed template

Target Learners¶

• higher education students

Target Learning Goals¶

• conceptual interpretation
• evaluative judgement
• epistemic integrity

Affordances¶

• Llm Critical Thinking Pedagogical Framework

Related Strategies¶

• Teach prompting and AI literacy as epistemic practice with structured guidance
• Counter-prompting: deliberately probing AI systems for their assumptions and using responses as data about the apparatus
• Make the distribution of epistemic responsibility an explicit object of instruction, including think-first routines before consulting the AI

Examples¶

-

Key Sources¶

• Mireia Vendrell, Samantha-Kaye Johnston. (2026). Scaffolding critical thinking with generative AI: Design principles for integrating large language models in higher education. Computers and Education: Artificial Intelligence. https://doi.org/10.1016/j.caeai.2026.100572